Tag: radiologists

CT Lung Screening Variation

Posted on by Brian Casey

Adoption of low-dose CT lung cancer screening is growing, and that’s a good thing. But rising LDCT utilization is also creating new challenges, illustrated by a new study in JACR that found high variability in radiologist interpretations. 

CT lung screening participation rates are rising, from single digits a decade ago to 19% in a recent survey. 

  • But there’s still a long way to go to get lung screening to the roughly 75% participation rate seen with breast cancer screening. 

One barrier to getting more people screened is false positives, which can cause patient anxiety and trigger a cascade of additional exams and procedures to work up suspicious findings. 

  • A major contributor to false positives may be variability in how radiologists read CT scans, so the JACR researchers investigated how interpretations for the same images changed between imaging specialists. 

Researchers looked at interpretations made by 1.4k radiologists, each of whom read a minimum of 50 LDCT screening exams (a total of 200k exams), then calculated false-positive rates for both baseline and follow-up exams. Researchers found…

  • High variability in false-positive rates, from 11% to 22%.
  • In random pairs of radiologists, on average, one radiologist would have twice the odds of making a false-positive call as the other. 
  • Radiologists with false-positive rates higher than the median rate also unsurprisingly had higher sensitivity than those below the median (97% vs. 92%).

What’s causing the variation? It could be because some radiologists use image interpretation patterns that increase false positives but also catch more cancers. 

  • In statistical terms, researchers found that for baseline screens read by radiologists who were below the median false-positive rate, they would have about 100 fewer false-positive screens for one fewer true-positive cancer. 

Radiologist variability could be reduced through programs to standardize screening interpretation, such as those implemented in mammography screening.

  • These could include support tools, automated feedback systems, educational interventions, and targeted double reading.

The Takeaway

The new findings on radiologist variability in reading CT lung cancer screening exams illustrate the delicate balance between detecting more cancer at the risk of producing additional false positives. Is the tradeoff worth it? We think we know how most patients would feel.

Rating CT Image Quality

Posted on by Brian Casey

As radiology strives to reduce CT radiation dose, one of its challenges is maintaining image quality while keeping dose low. A new five-star system for rating images is described in a new paper in EJR and could offer a solution by establishing an easy-to-understand global metric.

The radiology community has been making progress in reducing CT radiation dose, but much work remains to be done.

  • In particular, radiology professionals struggle between the desire for better-looking images – which usually result from higher radiation dose – with low-dose images that may be noisier but are good enough to make a diagnosis.

While there are lots of metrics for measuring radiation dose, image quality doesn’t have a widely recognized scale. 

  • So a team from the IAEA and MGH worked together to develop one, based on the widely recognized five-star paradigm for ranking consumer-facing businesses. 

In an interesting wrinkle, the five-star system acknowledges the dose dilemma, essentially penalizing images in which too much radiation dose was used to produce an image that’s crisper than what’s needed for diagnosis. 

  • On the other hand, the system rewards images that might be noisy due to use of less radiation, but that are still diagnostic.

 The system’s ratings are as follows…

  • Five stars – Acceptable, despite high image noise associated with low-dose CT.
  • Four stars – Acceptable for all parts within the region of interest.
  • Three stars – Acceptable, despite unintended high noise and/or some artifacts.
  • Two stars – Excellent quality with unjustifiably low image noise and no artifacts.
  • One star – Non-diagnostic, due to excessive noise or artifacts, or poor contrast.

To test the rating scale, IAEA and MGH researchers performed a study at six hospitals across five European countries. 

  • CT scans of 2.7k adults were acquired, and three radiologists per hospital were trained in the five-star scale and scored the images to see how reader subjectivity affected the scoring. 

The study found… 

  • Reader concordance was up to 93% at some sites, indicating little variability in scoring.
  • Overall discordance was rare, at 1.6%.
  • The two-star ratings (in which too much radiation was used) were associated with higher radiation dose in nearly all patient weight groups. 

The Takeaway

The new study shows that a five-star system for rating CT image quality is feasible and can reveal cases of unnecessarily high radiation dose. The question is whether the system remains an interesting thought experiment, or if it becomes an integral part of radiology’s effort to better manage radiation.

Radiology Report Turnaround Slows

Posted on by Brian Casey

Radiologists are taking longer to interpret medical images than they did 10 years ago … and it’s a problem that appears to be getting worse. New data from the ACR’s Neiman HPI group, published in JACR, show that report turnaround times rose 27% between 2023 and 2024.

Report turnaround time (commonly referred to as TAT) is a closely watched barometer of radiologist productivity, and longer TAT could indicate radiologists are struggling to keep up with growing imaging volumes.

  • Another Neiman HPI study on TAT released earlier this year discovered a “hockey stick” effect, with turnaround times jumping sharply starting in 2022. 

But that study only tracked TAT through 2023. Meanwhile, anecdotal reports have surfaced of a “rapid increase” in turnaround times in late 2024.

  • So the updated research adds more recent data, analyzing newly available Medicare fee-for-service claims from 2024.

Researchers analyzed data from 2.9M office and hospital outpatient claims from 2014 to 2024, finding that TAT…

  • Grew just 14% in seven years from 2014 to 2021 (0.091 to 0.104 days).
  • But then rose at double-digit annual rates in 2023 (60%) and 2024 (27%).
  • Reached 0.251 days by the end of 2024, a 177% increase over 10 years. 
  • Increased at different rates by modality over the 10-year period, including CT (381%), MRI (278%), ultrasound (267%), and X-ray (126%). 

Why did TAT growth decelerate in 2024 over the year before? The Neiman HPI authors weren’t sure, but they said practice leaders may have taken steps to meet higher demand, like moonlighting and reactivating retired staff.

  • But these aren’t long-term measures that can meet the mismatch between supply and demand, suggesting instead that “the radiology workforce may be operating at or near maximum capacity.”

The Takeaway

The new data on slower radiology report turnaround times confirm fears that radiologists are struggling under rising imaging volumes and a stagnant workforce. While slower TAT growth in 2024 is a bit of a silver lining, it does little to hide the growing storm clouds on the horizon.

Rads Flee VA After Agency Banned Remote Work

Posted on by Brian Casey

A new report claims that radiologists fled the U.S. Department of Veterans Affairs health system after the agency eliminated policies allowing remote work in 2025. While the VA has since rescinded the ban, the article in The American Prospect claims that plummeting morale continues to plague the health system’s radiologists.

The VA’s Veterans Health Administration operates one of the largest health systems in the U.S., serving some 9.1M veterans through 170 VA medical centers and affiliated outpatient sites across the country.

  • While there are no official figures, estimates suggest the VA employs at least 1.5k radiologists, or 4%-5% of all active U.S. radiologists.

While radiologist salaries at the VA don’t approach levels found in the private healthcare sector, many imaging specialists are drawn to the system thanks to perceptions that it offers more job security and stability, as well as its mission in serving the nation’s veterans.

  • But the VA’s image of stability began changing in January 2025, the article claims, when the Trump Administration ordered federal employees to return to working in offices.

The order hit VA radiology particularly hard. Thanks to PACS and teleradiology, remote image interpretation has become a staple of the average radiologist’s workday.

  • Remote reading is even seen as a possible solution to radiology’s rising imaging volume and stagnant workforce. 

So it’s no surprise that VA radiologists recoiled against the new policy, which “ignored the realities of radiology work” and caused morale to plummet among the health system’s imaging specialists.

  • The VA eventually recognized its mistake and rescinded the in-office requirement for radiologists. But by then the damage was done. 

The article claims that VA radiology has experienced ongoing repercussions from the turmoil…

  • Many radiologists have left for the private sector, where average salaries are over 40% higher. 
  • Workloads for the remaining VA radiologists have skyrocketed.
  • Primary care physicians are reporting it now takes “days, not hours,” to get imaging results.
  • VA medical centers are being forced to outsource some specialized scans like amyloid PET exams, for which turnaround times are stretching to two or three months.

The Takeaway

It’s hard to tell exactly how many radiologists have left the VA health system, but any job loss is significant for a provider with a mission as important as the VA’s. While the agency’s turnaround on remote work is welcome, it’s likely that the country’s veterans will bear the brunt of the VA’s misguided policy change for years to come.

CT Radiation Dose Drops in Nationwide Survey

Posted on by Brian Casey

Some good news arrived this week in the campaign to reduce CT radiation dose. A new nationwide survey in Radiology found that radiation dose from CT scans has fallen markedly over the past decade in the U.S.

CT has been radiology’s workhorse modality since the 1980s thanks to its winning combination of cost-effectiveness and diagnostic power. 

  • But radiation dose has always been the modality’s Achilles heel. That was highlighted by a controversial 2025 paper claiming that routine CT could cause over 100k cancers in a year in the U.S.

There are plenty of technologies that effectively reduce CT radiation dose, but the trick has always been getting clinicians to use them. 

  • Another problem is standardizing best-practice CT protocols, so there’s less variation in radiation dose between CT scanners in the same health system or institution. The key to standardization is establishing best-practice benchmarks.

A landmark study published almost 10 years ago got the ball rolling by tracking radiation dose in 2014, producing key metrics like diagnostic reference levels (DRLs) and achievable doses (AD) for 1.3M exams at 583 U.S. CT sites.

  • DRLs represent the 75th percentile of dose distribution, while ADs are set at the 50th percentile, and both numbers represent targets for dose optimization efforts that are dynamic and can change over time. 

In the current study, researchers updated the radiation knowledge base with new data from 5.2M CT exams at 592 U.S. facilities, a 4X larger sample than in 2014, finding…

  • Overall radiation dose fell by 22% as measured by volume CT dose index (CTDIvol) and by 20% using dose-length product, another common radiation measure.
  • The largest dose reductions came in chest CT with contrast (-31%) and chest CT without contrast (-27%), while head CT without contrast fell 3.5%. 
  • New levels of achievable dose benchmarks were set for a variety of CT exams, giving CT facilities new targets for radiation dose reduction that are in some cases as much as 19% lower than 2014 targets.

The Takeaway

The new findings on CT radiation dose reduction are a welcome counter to recent studies that have whipped up hysteria around medical radiation. But now is no time to take the foot off the pedal – radiology must continue to drive dose lower through a combination of new technologies and judicious protocol standardization.

AI Closes Mammo Gap Between Generalists, Specialists

Posted on by Brian Casey

Mammography screening exams are some of the most challenging medical images to interpret, but due to staffing issues many mammograms are read by general radiologists rather than specialists. A new study in Radiology found that an AI-based workflow helped close the gap, leading to a 25% improvement in the cancer detection rate for general radiologists.  

Most of the big population-based studies on mammography AI have been conducted in Europe, where breast screening is performed under a double-reader paradigm that has two radiologists interpreting exams.

  • In this scenario, studies have shown that AI can eliminate the need for a second reader, cutting workforce requirements with the same or even better cancer detection rates.

But U.S. breast screening programs don’t use double-reading, leaving many to wonder where AI fits into the single-reader paradigm – especially when that reader is a general radiologist with no breast fellowship training. 

  • The new study offers some clarity. Researchers developed an AI-based workflow that integrated DeepHealth’s ProFound Pro 2.x deep-learning application into DBT-based screening programs. 

They set up AI as a “safeguard review.” After a radiologist’s initial interpretation, AI analyzed non-recalled mammograms for suspicion of cancer. Exams that exceeded ProFound’s risk threshold were flagged and routed to an expert reviewer.

  • If the reviewer agreed with AI, the original interpreting radiologist was consulted and had final authority on whether to recall the case. 

The safeguard review concept was tested at 109 breast imaging facilities that saw 578k DBT mammography exams from 2021 to 2022. In particular, researchers focused on the impact the safeguard review had on interpretation accuracy of both specialists and general radiologists, finding…

  • The cancer detection rate of generalists improved 25%, from 3.76 to 4.99 cancers per 1k exams.
  • The CDR of specialists did not change at a statistically significant level (from 4.47 to 4.76, p = 0.33).
  • There was no statistically significant difference between AI-aided generalists and specialists.
  • Generalists became more efficient at cancer detection, as evidenced by 15% improvement in their positive predictive value (from 3.38% to 3.89%). 
  • Although generalists’ recall rates did increase with AI (from 9.06% to 10.4%). 

The Takeaway

The new study offers an intriguing look at how AI can be integrated into U.S. breast screening programs without dramatically disturbing workflow. It also shows how diagnostic performance can be improved in an environment where general radiologists are being asked to fly solo in an area they didn’t train in.

Lung Cancer Mystery in Non-Smokers

Posted on by Brian Casey

One of the emerging mysteries around lung cancer is why it occurs so often in people who don’t smoke – particularly in Asia. A new paper in JAMA Network Open investigates the phenomenon by presenting results from South Korea indicating that established screening criteria would have missed nearly two-thirds of lung cancer patients.

From its earliest days, CT lung screening has been targeted at heavy smokers who have the greatest chance of developing lung cancer.

  • Risk-based criteria determine who should be screened, usually based on some metric of smoking history (such as the USPSTF’s 20-pack-year threshold).

But many countries that have had national lung screening programs in place for a while – mostly in Asia – are learning that lung cancer also occurs in people who have never smoked at all. 

  • Whether and how to screen these individuals has become the subject of debate. 

In the current study, researchers from South Korea examined 89.9k patients who were diagnosed with lung cancer from 2013 to 2018, just before the country started its national lung screening program in 2019. 

  • Researchers focused on whether patients would have been eligible for screening under established criteria, such as from the USPSTF, ACS, and NCCN.

Among people diagnosed with lung cancer…

  • 65% would not have been eligible for lung screening under international guidelines. 
  • 44% had no smoking history. 
  • Screening eligibility differed sharply by sex, with men eligible at far higher rates than women (57% vs. 2.3%).
  • Smokers who weren’t eligible for screening had 5% lower rates of all-cause mortality and 4% lower lung cancer-specific mortality than smokers who were.
  • People who had never smoked had 14% lower rates of both all-cause and lung cancer-specific mortality. 

The data point out an interesting dilemma inherent in CT lung cancer screening, which from the outset was set up to be risk-based rather than population-based like mammography to avoid many of screening’s downsides, like overdiagnosis.

  • But that approach is missing many people who would otherwise benefit from screening, especially as we learn more about the elevated risk among many non-smoking populations, such as East Asian women.

The Takeaway

The new study shows momentum building toward broader CT lung cancer screening criteria that go beyond smoking status. The question is how quickly such criteria are adopted, and whether they gain traction outside of Asia, where recognition of lung cancer among non-smokers is growing.

Your Reporting Platform Is Now Your AI Strategy

Posted on by Partner Content

By Sheela Agarwal, MD, MBA, a practicing radiologist and chief medical information officer at Microsoft 

For most of my career, the radiology reporting platform was a workflow tool. Today, it is an AI strategy, and the way we evaluate it must change with it. 

I see that from two sides. As a practicing radiologist, I live in the reporting workflow. As CMIO at Microsoft, I help shape how technology serves it. 

  • The platform underlying radiology reporting now determines something bigger than features. It determines how effectively AI is integrated into the workflow and where it is making the biggest impact, for both radiologists and the care patients receive.  

The pressure is real, and it is human. Imaging volumes keep climbing while the workforce to read images struggles to keep pace, and the cognitive load on every radiologist grows with it. 

  • The question is no longer whether to adopt AI. It is which foundation can carry AI reliably, study after study. 

Most reporting solutions were not built to be that foundation. PowerScribe One is. The proof is in the scale: 

  • 280+ organizations, proven across IDNs, academic centers, community hospitals, and independent practices. 
  • 10,000+ radiologists have made PowerScribe One part of how they work. 
  • 10M+ reports every month, a volume that reflects real, sustained use. 

That scale is not the point on its own. It is evidence that the technology delivers where it counts. What matters to a radiologist is more specific: does it lighten a heavy worklist, or just add another click? 

As an AI companion to PowerScribe One, Dragon Copilot builds on that foundation, bringing prior reports, patient context, and information from credible sources to the same screen as they read, so radiologists work with a more complete picture without leaving their workflow. 

  • The deeper value is what it frees radiologists to do: practice at the top of their license, spending less time on the mechanics of report creation and more on the complex reads and the diagnostic judgment that shape a patient’s care. 

A reporting platform must be ready for what comes next, evolving alongside radiology and AI. 

  • For organizations still on PowerScribe 360, now is the time to evaluate the path forward. Migration to PowerScribe One preserves existing workflows and configurations, allowing organizations to modernize at their own pace without disrupting care. 

The Takeaway 

This is not simply a radiology reporting system upgrade. It is choosing a partner committed to practical innovation, built on decades of workflow expertise and deep collaboration with customers and partners. Connect with Microsoft’s team or click here to learn more about PowerScribe One and Dragon Copilot.

Ultrasound and DBT Screening — Time to Call It Quits?

Posted on by Brian Casey

Ultrasound long ago carved out a role in breast cancer screening as a complementary tool to conventional 2D mammography. But is ultrasound still needed, now that U.S. breast screening programs have largely switched over to 3D digital breast tomosynthesis (DBT)? A new study in Academic Radiology raises questions. 

Conventional 2D mammography has well-known shortcomings, particularly in women with dense breast tissue that can obscure lesions. So alternative modalities like ultrasound, breast MRI, and contrast-enhanced mammography (CEM) are called in to help when needed.

  • Past research has shown that supplemental ultrasound can improve the cancer detection rate (CDR) in a 2D mammography screening program by 3-4 cancers per 1k women. 

But those studies were performed before the switch to DBT, which can often see around overlapping structures thanks to a gantry head that acquires multiple images as it pans across the breast. 

  • So is ultrasound still needed in screening programs using DBT? Researchers from Weill Cornell Medicine at New York-Presbyterian Hospital tested the hypothesis by examining 103k screening exams from 2014 to 2024 in which both DBT and ultrasound were used. 

In the study, researchers found that screening ultrasound after a negative DBT result…

  • Generated 1.9k biopsies, or 19 biopsies for every cancer the modality detected.
  • Produced an additional cancer detection rate of 1.0 per 1k women, compared to an additional CDR of 3-4 cancers for ultrasound in the 2D mammography era. 
  • Had an overall false-positive screening rate of 98.5%, a false-positive biopsy rate of 94.8%, and a positive predictive value of biopsies performed (PPV3) of just 5.2%.
  • Generated $652k false-positive screening ultrasound costs and $1.16M in ultrasound-guided biopsy costs.

The numbers are sobering and indicate that the days of ultrasound as a supplemental screening modality to DBT screening could be coming to a close. 

  • Instead, the researchers recommended that ultrasound screening be replaced by more sensitive modalities like breast MRI or CEM, both of which are fortunately more available now than during the 2D mammography era.

The Takeaway

The new study answers the question – in the negative – of whether supplementary ultrasound is still needed in the era of DBT screening. The positive subtext here is that the research confirms the improved detection performance of 3D compared to 2D mammography.

MRI for Prostate Cancer Staging

Posted on by Brian Casey

Digital rectal exams for prostate cancer staging could become a thing of the past thanks to MRI. A new study in JAMA Network Open found that MRI performed as well as digital exams in determining the extent of prostate cancer disease.

Prostate cancer screening is moving closer to becoming a more widely accepted test, and MRI has played a major role in that evolution by enabling more precise workup of men with high PSA levels.

  • But what about other aspects of prostate cancer diagnosis and treatment, such as staging men found to have clinically significant disease? It turns out MRI has a role to play there as well. 

To learn more, researchers from Germany looked at data from 4.4k men with a median age of 66 and median PSA level of 7.4 ng/mL (anything over 3 ng/mL is typically referred for additional workup). All patients were scheduled for radical prostatectomy. 

  • Patients received digital rectal exams to assign clinical T stage and assess characteristics of cancer severity, such as local tumor extent, extracapsular extension, and seminal vesicle invasion. 

This was compared to multiparametric MRI scans on 1.5T or 3T systems, with data reported using the PI-RADS scale. The study’s primary outcome was distant metastasis-free survival. 

Among the patient cohort, researchers found…

  • MRI staging was slightly more accurate than digital exams for predicting biochemical recurrence-free survival (C index = 0.62, with 0.5 representing chance-level prediction and 1 indicating perfect prediction). 
  • And MRI was also better at predicting distant metastasis-free survival (C index = 0.67).
  • But MRI and digital exams were comparable when using four of the major prostate cancer risk classification systems in Europe.

What to make of the results? MRI didn’t have a huge advantage over digital rectal exams, but it was good enough for the authors to suggest that digital exams could be eliminated in favor of MRI workup instead.

  • That would enable clinicians to avoid many of the digital exam’s shortcomings, such as subjectivity, operator dependency, and restricted ability to assess extracapsular extension or seminal vesicle invasion.

The Takeaway

This week’s study shows that MRI’s role in prostate cancer diagnosis and treatment goes beyond just screening, and the digital rectal exam’s role for patient staging could soon become a thing of the past in all but a few cases. 

Get every issue of The Imaging Wire, delivered right to your inbox.